Stuart Russell
speaker
1,902 appearances
3 recordings
3 series
first heard Dec 2018
last heard 24 Jun
Stuart Russell’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 2 in all, peaking in Jun 2026 with 1.
Appearances
And so far, we haven't figured out a way to do it.
One theoretical possibility would be to build a very faithful simulation of the world and try out different objectives and see how did that go.
But that presumes that they can tell
what counts as things going wrong, but they can't do that unless they have the right objective, which you've already assumed that they don't.
So this is often a fallacy that we see, that people, for example, Steven Pinker is a very famous cognitive scientist from Harvard, and he says, but you're talking about superintelligence,
How could it be super intelligent if it doesn't realize that things are going wrong?
And the point is that super intelligence and objectives, they're sort of orthogonal in the sense that I can have a very, very intelligent system
that has a different objective from the one you might think it ought to have.
Imagine aliens, right?
They might be very intelligent, but they don't have human wellbeing as their objective, right?
They have alien wellbeing.
Cockroaches might be very intelligent, but they don't think much of humans.
So it's perfectly possible that the super intelligent system sees that humans are very unhappy with the way things are going, but it's been given its objective.
And if its objective didn't include
the things that are going wrong, then they don't count as going wrong.
It's unfortunate for these humans who are making a lot of noise about it, but I have the objective, so I'm just going to optimize it.
That's exactly what we have to get away from.
And so my approach has been to say, is there a way of building AI systems that's different from the standard model?
And the idea I came up with... I.e.
They're objective-based in a different way.
Showing 121–140 of 1,902 · page 7 of 96
← Previous
Next →